Ikibazo gihuza ibibazo · Hagati Urwego

ELMo Ikibazo Cyibisobanuro Byibibazo

Ongera usubiremo uburyo imvugo ya ELMo yerekana ibyerekezo ikora imvugo-yijambo ryumvikana kandi igahuza ibice byisubiramo kubikorwa byo hasi.

Inzira zijyanye no kuyoboraElmo Ibishushanyo mbonera
Ikibazo 1 Bya 8

Ni irihe tandukaniro nyamukuru riri hagati ya ELMo no gushiramo mbere nka Word2Vec?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni irihe tandukaniro nyamukuru riri hagati ya ELMo no gushiramo mbere nka Word2Vec?
    • ELMo itanga ijambo rimwe ibice bitandukanye ukurikije interuro yayo
    • ELMo ikoresha ibice bito
    • ELMo ikora gusa kumagambo amwe, ntabwo interuro
    • ELMo ntisaba amakuru yamahugurwa
  2. Ni ubuhe bwubatsi bwubaka ELMo ikoresha mugusoma inyandiko?
    • Guhindura hamwe no kwiyitaho
    • Icyerekezo cyimbitse cya LSTM y'ururimi
    • Umuyoboro w'amashusho
    • Umuyoboro woroheje
  3. Nigute ELMo ihuza ibice byayo imbere kumurimo wo hasi?
    • Ikoresha gusa urwego rwo hejuru
    • Ugereranije ibice byose bingana kandi bikosora ibisubizo
    • Ikoresha wize, umurimo-wihariye uremereye guhuza ibice byose
    • Itora igipande kimwe kuri buri gihe
  4. Niki ELMo ikoresha nkibice byinjiza kugirango ikore amagambo atagaragara?
    • Ijambo-ryose rishakisha gusa
    • Indangamuntu zihamye
    • Byte-couple-yashizwemo subwords kuva BERT
    • Imiterere-urwego rwa CNN
  5. Hafi ya ELMo yatangijwe ryari kandi nande?
    • 2018, n'ikigo cya Allen Institute for AI
    • 2013, na __AIU_PROTECTED_11 __ itsinda rya Word2Vec
    • 2020, na OpenAI
    • 2015, na Facebook AI
  6. Which corpus was used to train the bidirectional language model described in the ELMo paper?
    • The One Billion Word Benchmark
    • The Penn Treebank only
    • A corpus of labeled images
    • The GloVe Common Crawl vectors
  7. What language-model prediction does ELMo's forward LSTM learn?
    • Predicting the previous word from future context
    • Assigning a fixed vector to every document
    • Predicting the next word from the preceding context
    • Predicting a sentence's image resolution
  8. What linguistic information do ELMo's lower and higher LSTM layers tend to capture?
    • Lower layers encode image color, while higher layers encode audio pitch
    • Every layer stores only word frequency and ignores context
    • Higher layers are always limited to punctuation prediction
    • Lower layers tend toward syntax, while higher layers capture more context-dependent semantics